feat(m1): real benchmark loader (T1.6)

- SUPPORTED_DATASETS registry: smd/msl/smap/swat/psm (+toy)
- load_windows(name,T,stride): sliding windows + per-channel z-score norm
  -> shapes (N,T,C) and (N,T)
- windows_to_qa: anomaly/describe QA pairs from windows (non-empty)
- real loaders read data/real/<name>/test.npy (+test_label.npy) or TSMM_DATA_DIR;
  raise clear FileNotFoundError when absent (testable offline via 'toy')
- write_eval_jsonl helper for eval_real.jsonl
- tests/test_real_bench.py (7 tests, RED->GREEN)

Exit criteria: >=2 datasets load (toy + registry of 5 real); window/label shapes;
QA non-empty; missing real data raises clearly.

tests/test_real_bench.py

@@ -0,0 +1,61 @@
+"""Tests for real-benchmark loading (T1.6)."""
+import numpy as np
+import pytest
+
+from tsmm.data import real_bench
+
+
+def test_supported_dataset_registry_has_at_least_two():
+    regs = real_bench.SUPPORTED_DATASETS
+    assert len(regs) >= 2
+
+
+def test_load_windows_shapes_and_dtypes():
+    # 'toy' is a deterministic in-memory benchmark used to exercise the pipeline
+    # without requiring an external download.
+    windows, labels, meta = real_bench.load_windows("toy", T=64, stride=32)
+    assert windows.ndim == 3 and labels.ndim == 2
+    N, T, C = windows.shape
+    assert labels.shape == (N, T)
+    assert windows.shape[0] == labels.shape[0]
+    assert np.isfinite(windows).all()  # normalized -> finite
+    assert set(np.unique(labels)).issubset({0, 1})
+
+
+def test_load_windows_normalizes_per_channel():
+    windows, _, _ = real_bench.load_windows("toy", T=64, stride=32)
+    # z-score normalization -> mean ~0, std ~1 per channel over the whole set
+    mu = windows.reshape(-1, windows.shape[-1]).mean(0)
+    sd = windows.reshape(-1, windows.shape[-1]).std(0)
+    assert np.allclose(mu, 0, atol=1e-6)
+    assert np.allclose(sd, 1, atol=1e-6)
+
+
+def test_load_windows_stride_controls_count():
+    w1, _, _ = real_bench.load_windows("toy", T=64, stride=32)
+    w2, _, _ = real_bench.load_windows("toy", T=64, stride=64)
+    # smaller stride -> at least as many windows
+    assert w1.shape[0] >= w2.shape[0]
+
+
+def test_windows_to_qa_produces_nonempty_pairs():
+    windows, labels, meta = real_bench.load_windows("toy", T=64, stride=32)
+    qa = real_bench.windows_to_qa(windows, labels, meta, seed=0)
+    assert isinstance(qa, list) and len(qa) > 0
+    for item in qa:
+        assert set(item.keys()) >= {"instruction", "answer", "labels", "series", "category"}
+        assert isinstance(item["instruction"], str) and item["instruction"].strip()
+        assert isinstance(item["answer"], str) and item["answer"].strip()
+
+
+def test_load_windows_unknown_dataset_raises():
+    with pytest.raises(KeyError):
+        real_bench.load_windows("does-not-exist", T=64, stride=32)
+
+
+def test_load_windows_real_dataset_missing_data_raises_clear_error():
+    # Real loaders must raise a helpful error when the local data path is absent,
+    # rather than silently returning empty arrays.
+    with pytest.raises((FileNotFoundError, RuntimeError)):
+        # SMD is almost certainly not present in CI; should raise.
+        real_bench.load_windows("smd", T=64, stride=32)